Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    titles and positions of authority or religious significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æľĭ
    -0.16
    ÃŃÅ¡
    -0.15
    amework
    -0.15
    urd
    -0.14
    .si
    -0.13
    mpar
    -0.13
    erre
    -0.13
    ruž
    -0.13
    ëĦĪ
    -0.13
    akeup
    -0.13
    POSITIVE LOGITS
     Emer
    0.17
     John
    0.15
    ingu
    0.15
    ãĥ¼ãĥł
    0.15
    avin
    0.15
    åĢij
    0.15
     Dense
    0.14
     صاØŃب
    0.14
    们
    0.14
    _P
    0.14
    Act Density 0.126%

    No Known Activations